仓库机器人遇障测试:LLM 推理时感知还能否按时刹车?

krishnan · x · 2026-11-18

krishnan proposes a test (not a reported SiMa deployment): a warehouse robot hits an unexpected obstruction mid-reasoning-request. Under combined load, do perception and the stop response still meet deadlines? Speculative decoding speeds up tokens but doesn't prove perception stays fresh during long reasoning — the first question a buyer should ask.

所属事件:krishnan 质疑 SiMa Palette 3.0:单芯片跑感知+LLM 的机器人安全账(8 条相关)→

原文链接 →

「具身」频道最新

更多「具身」频道 AI 资讯 →